Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 500 899 100 409 606 309 608 631 721  41 398 561 754 463 706 277 131 888 533 305
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 899 721  NA 131  NA  41 888 631 500 533 606 305 398 463 100 561  NA 754 608 277 409 309 706
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 1 5 1 5 2 4 1 3 1 5
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "t" "s" "h" "z" "n" "O" "F" "U" "D" "Q"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
integer(0)
which( manyNumbersWithNA > 900 )
integer(0)
which( is.na( manyNumbersWithNA ) )
[1]  3  5 17

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
integer(0)
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
integer(0)
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
integer(0)

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "O" "F" "U" "D" "Q"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "t" "s" "h" "z" "n"
manyNumbers %in% 300:600
 [1]  TRUE FALSE FALSE  TRUE FALSE  TRUE FALSE FALSE FALSE FALSE  TRUE  TRUE FALSE  TRUE FALSE FALSE FALSE
[18] FALSE  TRUE  TRUE
which( manyNumbers %in% 300:600 )
[1]  1  4  6 11 12 14 19 20
sum( manyNumbers %in% 300:600 )
[1] 8

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" "large" NA      "small" NA      "small" "large" "large" "large" "large" "large" "small" "small"
[14] "small" "small" "large" NA      "large" "large" "small" "small" "small" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "large"   "UNKNOWN" "small"   "UNKNOWN" "small"   "large"   "large"   "large"   "large"  
[11] "large"   "small"   "small"   "small"   "small"   "large"   "UNKNOWN" "large"   "large"   "small"  
[21] "small"   "small"   "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1] 899 721  NA   0  NA   0 888 631 500 533 606   0   0   0   0 561  NA 754 608   0   0   0 706

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 1 5 2 4 3
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  1  5  2  4  3
duplicated( duplicatedNumbers )
 [1] FALSE FALSE  TRUE  TRUE FALSE FALSE  TRUE FALSE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 1
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 899
which.min( manyNumbersWithNA )
[1] 6
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 41
range( manyNumbersWithNA, na.rm = TRUE )
[1]  41 899

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 899 721  NA 131  NA  41 888 631 500 533 606 305 398 463 100 561  NA 754 608 277 409 309 706
sort( manyNumbersWithNA )
 [1]  41 100 131 277 305 309 398 409 463 500 533 561 606 608 631 706 721 754 888 899
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  41 100 131 277 305 309 398 409 463 500 533 561 606 608 631 706 721 754 888 899  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 899 888 754 721 706 631 608 606 561 533 500 463 409 398 309 305 277 131 100  41  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 899 721  NA 131  NA
order( manyNumbersWithNA[1:5] )
[1] 4 2 1 3 5
rank( manyNumbersWithNA[1:5] )
[1] 3 2 4 1 5
sort( mixedLetters )
 [1] "D" "F" "h" "n" "O" "Q" "s" "t" "U" "z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1]  8.0  1.5  4.5  4.5  4.5  8.0  1.5  8.0  4.5 10.0
rank( manyDuplicates, ties.method = "min" )
 [1]  7  1  3  3  3  7  1  7  3 10
rank( manyDuplicates, ties.method = "random" )
 [1]  9  2  5  4  6  8  1  7  3 10

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000  1.75914738 -0.14215858 -0.49714693
 [9]  1.17914620 -0.45587778 -1.86398126 -2.34252198  0.72980966  0.07787878 -2.02964882
round( v, 0 )
 [1] -1  0  0  0  1  2  0  0  1  0 -2 -2  1  0 -2
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  1.8 -0.1 -0.5  1.2 -0.5 -1.9 -2.3  0.7  0.1 -2.0
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  1.76 -0.14 -0.50  1.18 -0.46 -1.86 -2.34  0.73  0.08 -2.03
floor( v )
 [1] -1 -1  0  0  1  1 -1 -1  1 -1 -2 -3  0  0 -3
ceiling( v )
 [1] -1  0  0  1  1  2  0  0  2  0 -1 -2  1  1 -2

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 x 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2021 Biomedical Data Sciences (BDS) | LUMC